Hugging Face's logo

lesso07
/
c3861db8-33a8-412a-9eba-04c8aee89923

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso07 commited on
Commit
49caed3
•
1 Parent(s): faf44fd

Training in progress, step 100, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +203 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f47632850301c8f71ccdc08f968775eaf129bf4ecabba78b2f6b10e3d31e20e
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eea6a1891dcd66bc989c0469120e2a1a24ce8a34611833d9a995da558549297
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc3353e14d5bf03c981a048de4e82a6bbf5730cc2a55d6d4e36ff118f9c94437
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4edc78efa091bb8b5fe8f73a33859e9f1b7c3560a78b30916ddb6bba5949025b
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.1282051282051282,
5
  "eval_steps": 9,
6
- "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -604,6 +604,205 @@
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 11.736,
606
  "step": 75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
607
  }
608
  ],
609
  "logging_steps": 1,
@@ -618,12 +817,12 @@
618
  "should_evaluate": false,
619
  "should_log": false,
620
  "should_save": true,
621
- "should_training_stop": false
622
  },
623
  "attributes": {}
624
  }
625
  },
626
- "total_flos": 15277503283200.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.17094017094017094,
5
  "eval_steps": 9,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 11.736,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.12991452991452992,
610
+ "grad_norm": 0.3521919846534729,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 11.7479,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.13162393162393163,
617
+ "grad_norm": 0.3298490643501282,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 11.7393,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.13333333333333333,
624
+ "grad_norm": 0.33953893184661865,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 11.7373,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.13504273504273503,
631
+ "grad_norm": 0.4311155080795288,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 11.7605,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.13675213675213677,
638
+ "grad_norm": 0.39432641863822937,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 11.718,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.13846153846153847,
645
+ "grad_norm": 0.4806402027606964,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 11.7059,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.13846153846153847,
652
+ "eval_loss": 11.722899436950684,
653
+ "eval_runtime": 10.4786,
654
+ "eval_samples_per_second": 47.048,
655
+ "eval_steps_per_second": 5.917,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.14017094017094017,
660
+ "grad_norm": 0.32158151268959045,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 11.7167,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.14188034188034188,
667
+ "grad_norm": 0.34963464736938477,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 11.7343,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.14358974358974358,
674
+ "grad_norm": 0.42247357964515686,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 11.7288,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.1452991452991453,
681
+ "grad_norm": 0.36811158061027527,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 11.7335,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.147008547008547,
688
+ "grad_norm": 0.34688490629196167,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 11.715,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.14871794871794872,
695
+ "grad_norm": 0.3239607810974121,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 11.7475,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.15042735042735042,
702
+ "grad_norm": 0.35352712869644165,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 11.7133,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.15213675213675212,
709
+ "grad_norm": 0.3768596947193146,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 11.7051,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.15384615384615385,
716
+ "grad_norm": 0.37222838401794434,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 11.7127,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.15384615384615385,
723
+ "eval_loss": 11.721938133239746,
724
+ "eval_runtime": 10.2967,
725
+ "eval_samples_per_second": 47.879,
726
+ "eval_steps_per_second": 6.021,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.15555555555555556,
731
+ "grad_norm": 0.3459213674068451,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 11.7197,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.15726495726495726,
738
+ "grad_norm": 0.38420385122299194,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 11.718,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.15897435897435896,
745
+ "grad_norm": 0.4105149507522583,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 11.6946,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.1606837606837607,
752
+ "grad_norm": 0.406562477350235,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 11.705,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.1623931623931624,
759
+ "grad_norm": 0.3522111773490906,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 11.6961,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.1641025641025641,
766
+ "grad_norm": 0.397614985704422,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 11.7015,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.1658119658119658,
773
+ "grad_norm": 0.39191102981567383,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 11.7142,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.1675213675213675,
780
+ "grad_norm": 0.3441464900970459,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 11.7322,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.16923076923076924,
787
+ "grad_norm": 0.4079350531101227,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 11.7321,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.16923076923076924,
794
+ "eval_loss": 11.721770286560059,
795
+ "eval_runtime": 10.4665,
796
+ "eval_samples_per_second": 47.103,
797
+ "eval_steps_per_second": 5.924,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.17094017094017094,
802
+ "grad_norm": 0.3476838767528534,
803
+ "learning_rate": 0.0,
804
+ "loss": 11.7032,
805
+ "step": 100
806
  }
807
  ],
808
  "logging_steps": 1,
 
817
  "should_evaluate": false,
818
  "should_log": false,
819
  "should_save": true,
820
+ "should_training_stop": true
821
  },
822
  "attributes": {}
823
  }
824
  },
825
+ "total_flos": 20370004377600.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null